I have defended my PhD thesis titled “Distributional Regression Models with Application to Numerical Weather Prediction Forecasts” at the University of Hildesheim!

Distributional Regression Models

Statistical Learning

Simplified Vine Copulas

Probabilistic Forecasting

Ensemble Postprocessing

Author

David Jobst

Published

March 31, 2026

During my PhD, I have extended univariate and multivariate distributional regression models using statistical learning and studied these developments in simulation studies as well as in the context of postprocessing of numerical weather prediction forecasts. This has resulted into the following four papers contributing to my PhD thesis:

Jobst, D., A. Möller, and J. Groß (2024a). “Gradient-Boosted Generalized Linear Models for Conditional Vine Copulas”. In: Environmetrics 35.8. [doi | bib], p. e2887.
Jobst, D., A. Möller, and J. Groß (2025). “D-vine Generalized Additive Model copula-based quantile regression with application to ensemble postprocessing”. In: Journal of the Royal Statistical Society Series C: Applied Statistics 74.4. [doi | bib], pp. 994-1020.
Jobst, D., A. Möller, and J. Groß (2023). “D-vine-copula-based postprocessing of wind speed ensemble forecasts”. In: Quarterly Journal of the Royal Meteorological Society 149.755. [doi | bib], pp. 2575-2597.
Jobst, D., A. Möller, and J. Groß (2024b). “Time-series-based ensemble model output statistics for temperature forecasts postprocessing”. In: Quarterly Journal of the Royal Meteorological Society 150.765. [doi | bib], pp. 4838-4855.